The purpose of group project is to creating opportunities and evaluating the skills necessary for students to independently acquire new, challenging knowledge, leveraging all available resources in their environment, and doing so in a timely fashion because promptness is of utmost importance.
Students are required to self-organize into five-person groups to independently learn and execute a deep learning AI project promptly and resourcefully, with minimal supervision.
In this project, you have the freedom to choose a topic that truly ignites your passion, and select a project type that aligns with your interests.
The only criteria, it must be interesting, challenging, and ultimately useful to you.
Your passion will be your compass, guiding you on a journey of exploration and innovation.
Students typically undertake one of FOUR types of projects:
- Create Your Own Data and use an existing approach ⭐
- The main focus is on collecting data and making it useful for existing DL methods. A good example is that you collect some images and annotate them, and then train an existing image classifier to perform a specific task on these images
- Create Your Own Method on an existing dataset ⭐⭐
- Taking an existing dataset and adapting an existing method to make it your own DL method. You modify parameters, work with existing neural networks, apply what you've learned in the lecture, and aim to make them more efficient.
- Beat the Classics - Implement a DL method and compare to non-DL baseline ⭐⭐⭐
- Challenge the state-of-the-art using algorithms without DL or with DL algorithms that aim to surpass this baseline. Compare the results and demonstrate the ability to outperform the baseline, referred to as "beat”.
- Beat the Stars - Improve the state of the art ⭐⭐⭐⭐
- By selecting a research paper, the goal is to demonstrate how to outperform the current state-of-the-art papers. It's important to note that due to the rapid pace of paper publication, it might be difficult to stay up-to-date with the latest advancements. Nonetheless, the objective is to select a recent paper as a baseline and attempt to beat it.
It is very important for students to choose applications or research that they are interested in to explore deep learning of AI, which may bring many special ideas and new discoveries. Therefore, it is crucial to choose a project that ignites your passion and enthusiasm. Don’t hesitate to come up with ambitious ideas that excite you, and remember, if you need guidance on how to get started, we’re here to help.
Group Project Assessment:
- Project Team Formation (Week 3)
- Create a team of 5 people and choose a team leader.
- The team leader is responsible for submitting the group project assessment materials, such as member list, proposal, and final report.
- Send the list of team members and the elected team leader to the Instructor at eelmpo@cityu.edu.hk
- Deadline: Feb 2, 2024 2024
- Project Proposal (Week 4)
- A 5-page project proposal (not include references).
- Submit the project proposal in PDF format to CANVAS proposal assignment.
- Proposal must contain:
- Project Title
- Student Name, Student ID and Email Address of each member
- Summary with goals of the project in about 300 words.
- Other suggested content: The group proposal outlines the problem, objectives, methodology, dataset, baseline selection, experimental setup, timeline, evaluation plan, collaboration plan, risks, contingency plans, ethical considerations, and references for the group project. It serves as a roadmap, ensuring clarity and alignment among team members.
- References
- Deadline: 16th February 2024
- Oral Presentation (Week 12 and 13)
- The oral presentation assesses students' communication skills, including their ability to clearly convey project objectives, methodology, and findings. Their response to questions gauges their understanding of the project and role within the team.
- Every group is also required to make a 10-minute Power Point presentation of their group project to the entire class.
- The presentation must include:
- A short description of the project and its objectives
- An explanation of the implemented algorithm and relevant theory
- A demonstration of the working program – i.e., results obtained when running the program
- Final Report, PPT, Source Code and Demo Video (Week 14)
- The final project report should be 30-60 pages in length, including references. A final report template was provided here:
- Final_Report_Template
- The structure outlined in this template serves as a flexible guide rather than a rigid blueprint for the final report. While the chapters and sections presented here are commonly found in research theses or technical reports, the specific nature of the undertaken research may necessitate variations in structure. Additionally, the order of items within chapters can be adjusted accordingly. The template reflects the traditional technical report structure, which aims to demonstrate a coherent line of argument across six chapters: introduction, literature review, research design, results, discussion, and conclusions.
- Demo video is required to be a 3-4 minute summary of the project.
- Students are also required to submit the Python source code of any implementation and PPT of the oral presentation for assessment.
- The final report must include an Appendix A for “Individual Contributions of the Group Project”, in which students provide detailed information about each team member's contributions to the group project. This includes describing their responsibilities, the tasks they completed, and the outcomes they achieved. This appendix is important for assessing individual's performance in the group project, which is necessary for meeting the requirements of professional accreditation of the course.
- All the PPT, Final Report and Source Code are required to submit to CANVAS Group Project Final Report
- Deadline: 26 April 2024
Project Hints
- Your passion is your compass.
- A high-quality project for EE4016 would be one that has the potential to be published or nearly published. It is anticipated that some students will continue working on their projects even after completing the course, with the aim of submitting their work to conferences or journals. To gather inspiration, you can explore recent research papers in the field of deep learning, particularly from conferences like ICML and NeurIPS.
- Once you have identified a topic that interests you, it is beneficial to search for existing research on related subjects using academic search engines such as Google Scholar.
- Another crucial aspect of project design is identifying suitable datasets for your chosen topic. If the data requires significant preprocessing or you plan to collect it yourself, keep in mind that this is just one part of the overall project work and can often consume a substantial amount of time. Nonetheless, it is important to maintain a solid methodology and engage in thorough discussions of the results, so be mindful of pacing your project accordingly.
Presentation Schedule:
Section A (Week 12)
Group 3 : Voice-to-text transcription and gender analysis using recurrent
neural networks with novel optimization algorithms
- Ho Ka Ting, Kong To Lam, Kwok Tsz Lik Lik, Wong Ho Fan, Tang Chuen Yau
Group 4 : Image Classification using Convolutional Neural Networks
- Lam Hiu Chun, KIM Seung Gyu, WOO Sang Won, ZHAN Yipeng, Wong Man Hin
Group 5 : Image Classification using DL and Non-DL Baseline
- Cheung Cheuk Lun, Chung King Hong, Cheng Wing Yin, Ng Chi To, Tse Man Hin
Group 6 : Stock Price Prediction
- Pang Kin Lam , HUNG HIU SING, Hon Shing Hei, Chan Sau Lai, Chow Ho Chun
Group 7 : Machine Learning of image segmentation for growth rate measurement
- Chung Chi Kin, Man King Lung, Ng Long Hin, Chow Wai Lam, Tang Sin Tsun
Group 8 : An improved version of car damage detection and segmentation
- LI Zhuobin, PU Zixuan, LYU Tiansheng, GUO Yicheng, SIT Sing Yeung
Group 9 : TabulaVision
- Wu Ka Wing, Yeung Chak Kei, Mou Cheuk Hei, Lai Ka Yu, Tse Tin Hei Alfred
Group 10 : HKSL recognition with AI
- Ho Man Chung, Li Tsz Chun, Li Shing Cho, Mok Kim Tung, Yim Chun
Group 11: Pet Recognition in Machine Vision
- FAN Ziqi, XU Xiaopei, SHEUNG KA LEONG, DING Jinfeng, WENG Zekai
Group 2 : Multiple object recognition - Garbage Classification
- Zhang Shurong, Cheung Chun Wong, LUO Wenyu, Tai Long Ching, Lin Zifeng
Section B (Week 13)
Group 12 : Comparison with DL(CNNs) and non-DL(SVM) in Facial emotional recognition
- Lai Tsz Kin, Cheung Ka Sing, Chan Tsz Lok, Leung Chung Hei, HUANG Jianfeng
Group 13 : Spam Filtering with BERT-BiLSTM-CRF model
- Tam Kai Fung, Kwong Ho Yin, Chan Cheuk Fung, Yip Yan Sum Shirley, Wong Ho Ming
Group 14 : Enhancing Sentiment Analysis with Modified Transformer Networks
- Sin Yuk Yuen, Fung Kwan Tai, Tang Tsz Hung, Yeung Yu Hang, Li Yat Long
Group 15 : Solve CAPTCHA in text form using the classification technique, and analyze the recognition ability of machines
- Chan Chiu Hei, Lee Ka Hung, Yu Chun Tung, Chen Zhi Cheng, Wong Ka Chun
Group 16 : Real-ESRGAN Practical Resolution, Advanced Image Enhancement Tool
- XIAO Jiancheng, ALE Manisa, AFZAL Fatima Tul Zahra, TAM Ho Wang, WAN Chun Lok
Group 17 : Motion Control and Balance Control of Robots using Deep Reinforcement Learning
- LI Xinyao, LYU Guanlin, TONG Shuyao, DUAN WEILUN, MA Qiaochu
Group 18 : Facial expression and Micro-expression Recognition (FMER)
- Ng Kin Pui, Choi Yin Kin, Wong Tsz Ching, She Long Hei, Lam Tat Yan
Group 19 : Detection of Frauds in Financial Statements
- HUNG Farrell, JENATA Jeanitha, KAN Tin Long, WENAS Patrick, WONG Cham Fung
Group 20 : Micro-Expression Recognition Project - Unveiling Hidden Emotions
- NG Ka Long, NG Ka Wai, LUNG Ching Hei, SZE Hung Lam, CHU Pong Wai
Group 21: Recommender Systems – ML vs DL
- SHEN Hei Yi, CHEUNG Euwin, LAI Wing Sum, LAM Ting Kwan Alex, YAU Lap Sang Vincent
Group 22: Classification of First-generation Pokémon
-
Ng Lok Hang,Cheng Chit, WAN Ho Yeung, MUNIR Jalil, POON Ching Keung
Group 1 : Fake News Detection Project Using Machine Learning
- LEUNG Ting Hei, LAI Tsz Wing, MAN Chun Yin, LEUNG Chun Hin, HO Ki Him Edwin
